{ "openapi": "3.0.1", "info": { "title": "Substack Scraper", "description": "Download every post from any Substack newsletter: full article text, likes, comments, shares, author and subscriber count. Whole archive, any newsletter (including custom web addresses), date and keyword filters. Export to Excel, CSV or Google Sheets.", "version": "1.0", "x-build-id": "XjovKQnN9Pcqk9Y3C" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/dacoder~substack-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-dacoder-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/dacoder~substack-scraper/runs": { "post": { "operationId": "runs-sync-dacoder-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/dacoder~substack-scraper/run-sync": { "post": { "operationId": "run-sync-dacoder-substack-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "publications": { "title": "Substack publications, posts or authors", "minItems": 1, "uniqueItems": true, "type": "array", "description": "What to scrape. Each entry can be a publication URL (https://www.lennysnewsletter.com or https://astralcodexten.substack.com), a custom domain (www.noahpinion.blog), a subdomain name (astralcodexten), a single post URL (https://www.lennysnewsletter.com/p/some-post), or an author (@lenny or https://substack.com/@lenny, which scrapes their main publication).", "items": { "type": "string" } }, "maxPostsPerPublication": { "title": "Max posts per publication", "minimum": 1, "maximum": 1000000, "type": "integer", "description": "Stop after this many posts from each publication (after filters). Posts are fetched newest first unless you change the sort order. Set a large number (e.g. 100000) to get the whole archive.", "default": 100 }, "includeContent": { "title": "Include full post text", "type": "boolean", "description": "On by default. Fetches each post's full body as HTML, plain text and Markdown (charged as a small add-on per post). For paid posts you get the free part before the paywall, and isTruncated tells you if it was cut. Turn off to get only titles, dates, stats and previews: faster and cheaper.", "default": true }, "startDate": { "title": "Posts published after", "type": "string", "description": "Only posts published on or after this date. Use a date (2025-01-31) or a relative period (30 days, 6 months, 1 year)." }, "endDate": { "title": "Posts published before", "type": "string", "description": "Only posts published on or before this date. Use a date (2025-12-31) or a relative period (7 days)." }, "searchQuery": { "title": "Search within publications", "type": "string", "description": "Only posts matching this keyword search inside each publication (Substack's own archive search). Results are ordered by relevance." }, "audience": { "title": "Free or paid posts", "enum": [ "all", "free", "paid" ], "type": "string", "description": "Return all posts, only free posts, or only paid (subscriber-only) posts.", "default": "all" }, "postType": { "title": "Post type", "enum": [ "all", "newsletter", "podcast", "thread" ], "type": "string", "description": "Return all posts or only one type: newsletters (written posts), podcasts or threads.", "default": "all" }, "sortBy": { "title": "Sort order", "enum": [ "new", "top" ], "type": "string", "description": "Newest first, or the publication's most popular posts first.", "default": "new" }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Usually not needed: Substack's API works without a proxy. Use one only if you see repeated 403/429 errors.", "default": { "useApifyProxy": false } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }